> ## Documentation Index
> Fetch the complete documentation index at: https://nvd-54.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Microsoft Foundry 中间件集成

> 使用 LangChain Python 集成 Azure AI 中间件。

专为 Microsoft Foundry 和 Azure AI Content Safety 设计的中间件。了解更多关于[中间件](/oss/python/langchain/middleware/overview)的信息。

这些中间件类位于 `langchain-azure-ai` 包中，从 `langchain_azure_ai.agents.middleware` 导出。

<Info>
  Azure AI Content Safety 中间件目前在上游标记为实验性。随着 Azure AI Content Safety 和 LangChain 中间件支持的不断成熟，预计 API 接口会有所变化。
</Info>

## 概述

| 中间件                                       | 描述                                                                           |
| ----------------------------------------- | ---------------------------------------------------------------------------- |
| [Text moderation](#text-moderation)       | Screen input and output text for harmful content and blocklist matches       |
| [Image moderation](#image-moderation)     | Screen image inputs and outputs using Azure AI Content Safety image analysis |
| [Prompt shield](#prompt-shield)           | Detect direct and indirect prompt injection attempts                         |
| [Protected material](#protected-material) | Detect copyrighted or otherwise protected text or code                       |
| [Groundedness](#groundedness)             | Evaluate model outputs against grounding sources and flag hallucinations     |

### Features

* Text moderation for harmful content and custom blocklists.
* Image moderation for data URLs and public HTTP(S) image inputs.
* Prompt injection detection with Prompt Shield.
* Protected material detection for text and code.
* Groundedness evaluation for generated answers against retrieved context.
* Custom `context_extractor` hooks to adapt screening and evaluation to your agent state.

## 设置

To use the Azure AI Content Safety middleware, install the integration package, configure either an Azure AI Foundry project endpoint or an Azure Content Safety endpoint, and provide a credential.

### 安装

Install the package:

<CodeGroup>
  ```bash pip theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  pip install -U langchain-azure-ai
  ```

  ```bash uv theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  uv add langchain-azure-ai
  ```
</CodeGroup>

### 凭证

For authentication, pass either `DefaultAzureCredential()` or an API-key string through the `credential` argument. Using a Foundry Project requires the use of Microsoft Entra ID for authentication.

```python Initialize credential icon="shield-lock" theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from azure.identity import DefaultAzureCredential

credential = DefaultAzureCredential()
```

### 实例化

The middleware supports two endpoint styles:

* An Azure Content Safety resource endpoint via `AZURE_CONTENT_SAFETY_ENDPOINT`
* An Azure AI Foundry project endpoint via `AZURE_AI_PROJECT_ENDPOINT`

If both are available, prefer `project_endpoint` because it gives better defaults for Azure AI Foundry-based workflows. In most setups, you can set the environment variable once and omit `endpoint` or `project_endpoint` from each middleware instantiation.

```python Configure endpoint icon="key" theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import os

os.environ["AZURE_AI_PROJECT_ENDPOINT"] = "https://<resource>.services.ai.azure.com/api/projects/<project>"
```

Import and configure your middleware from `langchain_azure_ai.agents.middleware`.

```python Initialize middleware icon="arrows-shuffle" theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from azure.identity import DefaultAzureCredential
from langchain_azure_ai.agents.middleware import AzureContentModerationMiddleware

middleware = AzureContentModerationMiddleware(
    project_endpoint="https://<resource>.services.ai.azure.com/api/projects/<project>",
    credential=DefaultAzureCredential(),
    categories=["Hate", "Violence"],
    exit_behavior="error",
)
```

## Use with an agent

Pass middleware to [`create_agent`](https://reference.langchain.com/python/langchain/agents/factory/create_agent) in order. You can combine Azure AI middleware with [built-in middleware](/oss/python/langchain/middleware/built-in).

```python Agent with middleware icon="robot" theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from azure.identity import DefaultAzureCredential
from langchain.agents import create_agent
from langchain_azure_ai.agents.middleware import AzureContentModerationMiddleware

agent = create_agent(
    model="azure_ai:gpt-5.4",
    middleware=[
        AzureContentModerationMiddleware(
            project_endpoint="https://<resource>.services.ai.azure.com/api/projects/<project>",
            credential=DefaultAzureCredential(),
            categories=["Hate", "Violence"],
            exit_behavior="error",
        )
    ],
)
```

<Tip>
  If `AZURE_AI_PROJECT_ENDPOINT` is already set, you can usually omit `project_endpoint` during instantiation.
</Tip>

## Azure AI Content Safety

### Text moderation

Use `AzureContentModerationMiddleware` to screen the last `HumanMessage` before the agent runs and the last `AIMessage` after the agent runs. This middleware uses Azure AI Content Safety harm detection and can also check custom blocklists configured in your resource.

文本审核适用于以下场景：

* 在模型调用前阻止有害的用户输入
* 在模型输出到达最终用户前进行过滤
* 在受监管或企业部署中强制执行自定义阻止列表
* 使用不同的类别和方向设置组合多个审核通道

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from azure.identity import DefaultAzureCredential
from langchain_azure_ai.agents.middleware import AzureContentModerationMiddleware

middleware = AzureContentModerationMiddleware(
    project_endpoint="https://<resource>.services.ai.azure.com/api/projects/<project>",
    credential=DefaultAzureCredential(),
    categories=["Hate", "SelfHarm", "Sexual", "Violence"],
    severity_threshold=4,
    exit_behavior="error",
    apply_to_input=True,
    apply_to_output=True,
)
```

<Accordion title="配置选项">
  <ParamField body="categories" type="list[str] | None">
    Harm categories 提供自然语言接口alyze. Valid values are `'Hate'`, `'SelfHarm'`, `'Sexual'`, and `'Violence'`. Defaults to all four categories.
  </ParamField>

  <ParamField body="severity_threshold" type="int" default="4">
    Minimum severity score from `0` to `6` that triggers the configured behavior.
  </ParamField>

  <ParamField body="exit_behavior" type="string" default="error">
    One of `'error'`, `'continue'`, or `'replace'`.
  </ParamField>

  <ParamField body="apply_to_input" type="bool" default="True">
    Whether to screen the last `HumanMessage` before the agent runs.
  </ParamField>

  <ParamField body="apply_to_output" type="bool" default="True">
    Whether to screen the last `AIMessage` after the agent runs.
  </ParamField>

  <ParamField body="blocklist_names" type="list[str] | None">
    Names of custom blocklists configured in your Azure Content Safety resource.
  </ParamField>

  <ParamField body="context_extractor" type="Callable | None">
    Optional callable that extracts the text to screen from agent state and runtime.
  </ParamField>
</Accordion>

### Image moderation

Use `AzureContentModerationForImagesMiddleware` when your agent handles visual content. It extracts images from the latest input or output message and screens them with the Azure AI Content Safety image analysis API.

This middleware supports:

* Base64 data URLs such as `data:image/png;base64,...`
* Public HTTP(S) image URLs

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from azure.identity import DefaultAzureCredential
from langchain_azure_ai.agents.middleware import (
    AzureContentModerationForImagesMiddleware,
)

middleware = AzureContentModerationForImagesMiddleware(
    endpoint="https://<resource>.cognitiveservices.azure.com/",
    credential=DefaultAzureCredential(),
    categories=["Hate", "SelfHarm", "Sexual", "Violence"],
    severity_threshold=4,
    exit_behavior="error",
    apply_to_input=True,
    apply_to_output=False,
)
```

<Accordion title="配置选项">
  <ParamField body="categories" type="list[str] | None">
    Image harm categories 提供自然语言接口alyze. Defaults to all four supported categories.
  </ParamField>

  <ParamField body="severity_threshold" type="int" default="4">
    Minimum severity score from `0` to `6` that triggers the configured behavior.
  </ParamField>

  <ParamField body="exit_behavior" type="string" default="error">
    One of `'error'` or `'continue'`.
  </ParamField>

  <ParamField body="apply_to_input" type="bool" default="True">
    Whether to screen images in the latest `HumanMessage`.
  </ParamField>

  <ParamField body="apply_to_output" type="bool" default="False">
    Whether to screen images in the latest `AIMessage`.
  </ParamField>

  <ParamField body="context_extractor" type="Callable | None">
    Optional callable that extracts images from agent state and runtime.
  </ParamField>
</Accordion>

### Prompt shield

Use `AzurePromptShieldMiddleware` to detect prompt injection in user prompts and optional supporting documents. By default it screens input only, because prompt injection is usually an input-side attack, but you can also enable output screening.

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from azure.identity import DefaultAzureCredential
from langchain_azure_ai.agents.middleware import AzurePromptShieldMiddleware

middleware = AzurePromptShieldMiddleware(
    project_endpoint="https://<resource>.services.ai.azure.com/api/projects/<project>",
    credential=DefaultAzureCredential(),
    exit_behavior="continue",
    apply_to_input=True,
    apply_to_output=False,
)
```

<Accordion title="配置选项">
  <ParamField body="exit_behavior" type="string" default="error">
    One of `'error'`, `'continue'`, or `'replace'`.
  </ParamField>

  <ParamField body="apply_to_input" type="bool" default="True">
    Whether to screen the latest `HumanMessage` before the agent runs.
  </ParamField>

  <ParamField body="apply_to_output" type="bool" default="False">
    Whether to screen the latest `AIMessage` after the agent runs.
  </ParamField>

  <ParamField body="context_extractor" type="Callable | None">
    Optional callable that extracts the user prompt and grounding documents from agent state and runtime.
  </ParamField>
</Accordion>

### Protected material

Use `AzureProtectedMaterialMiddleware` to detect protected content such as copyrighted text or code. This middleware can screen both the latest user input and the latest model output.

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from azure.identity import DefaultAzureCredential
from langchain_azure_ai.agents.middleware import AzureProtectedMaterialMiddleware

middleware = AzureProtectedMaterialMiddleware(
    endpoint="https://<resource>.cognitiveservices.azure.com/",
    credential=DefaultAzureCredential(),
    type="code",
    exit_behavior="replace",
    apply_to_input=False,
    apply_to_output=True,
    violation_message="Protected material detected. Please provide a higher-level summary instead.",
)
```

<Accordion title="配置选项">
  <ParamField body="type" type="string" default="text">
    The content type to screen: `'text'` or `'code'`.
  </ParamField>

  <ParamField body="exit_behavior" type="string" default="error">
    One of `'error'`, `'continue'`, or `'replace'`.
  </ParamField>

  <ParamField body="apply_to_input" type="bool" default="True">
    Whether to screen the latest `HumanMessage`.
  </ParamField>

  <ParamField body="apply_to_output" type="bool" default="True">
    Whether to screen the latest `AIMessage`.
  </ParamField>

  <ParamField body="context_extractor" type="Callable | None">
    Optional callable that extracts text from agent state and runtime.
  </ParamField>
</Accordion>

### Groundedness

Use `AzureGroundednessMiddleware` to evaluate whether a model response is grounded in the context available to the agent. Unlike the other middleware classes on this page, groundedness runs after model generation and inspects the generated answer against supporting sources.

By default, groundedness collects sources from the current conversation, including system content, tool outputs, and relevant annotations attached to model responses.

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from azure.identity import DefaultAzureCredential
from langchain_azure_ai.agents.middleware import AzureGroundednessMiddleware

middleware = AzureGroundednessMiddleware(
    project_endpoint="https://<resource>.services.ai.azure.com/api/projects/<project>",
    credential=DefaultAzureCredential(),
    domain="Generic",
    task="QnA",
    exit_behavior="continue",
)
```

<Accordion title="配置选项">
  <ParamField body="domain" type="string" default="Generic">
    The analysis domain. Supported values are `'Generic'` and `'Medical'`.
  </ParamField>

  <ParamField body="task" type="string" default="Summarization">
    The task type for the analysis. Supported values are `'Summarization'` and `'QnA'`.
  </ParamField>

  <ParamField body="exit_behavior" type="string" default="error">
    One of `'error'` or `'continue'`.
  </ParamField>

  <ParamField body="context_extractor" type="Callable | None">
    Optional callable that extracts the answer, grounding sources, and optional question from agent state and runtime.
  </ParamField>
</Accordion>

## API 参考

For the full public API, see the middleware exports in [`langchain_azure_ai.agents.middleware`](https://github.com/langchain-ai/langchain-azure/tree/main/libs/azure-ai/langchain_azure_ai/agents/middleware) and the underlying Content Safety middleware package in [`langchain_azure_ai.agents.middleware.content_safety`](https://github.com/langchain-ai/langchain-azure/tree/main/libs/azure-ai/langchain_azure_ai/agents/middleware/content_safety).

***

<div className="source-links">
  <Callout icon="terminal-2">
    [Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
  </Callout>

  <Callout icon="edit">
    [Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/oss/python/integrations/middleware/azure_ai.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
  </Callout>
</div>